© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 68217
    Prev
    Next
    INDEX
    Explanations

    blood tests and measurements

    np_acts-logits-general · gemini-2.5-flash-lite

    medical test values and measurements, particularly those reporting numbers with units.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     to
    -1.84
     of
    -1.58
     acqua
    -1.45
    ͑
    -1.45
    本来
    -1.38
    億円
    -1.34
     it
    -1.34
     demandes
    -1.34
     their
    -1.31
     theſe
    -1.27
    POSITIVE LOGITS
     early
    1.49
     yesterday
    1.44
     advice
    1.34
     assist
    1.33
    ейчас
    1.32
     during
    1.31
    lámpara
    1.29
     Sử
    1.28
     indicating
    1.27
     assistance
    1.25
    Activations Density 0.261%

    No Known Activations